CoChat

Multimodal Emotion Recognition Using a Modified Dense Co-Attention Symmetric Network

Zhao, Zhi-Wei, Liu, Wei, Lu, Bao-Liang · 2021 · 2021 10th International IEEE/EMBS Conference on Neural Engineering (NER)

The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.

Abstract

In this paper, an attention-based network called modified Dense Co-Attention Symmetric Network is investigated to classify three human emotions using electroencephalogram (EEG), eye movement features (EYE), and raw eye movement image (EIG) data. The key idea of this model is to use a novel co-attention layer, which augments the weights of the critical feature channel and builds correlations among the different modalities. We stack the co-attention layer to form a hierarchy that strengthens the effect layer-by-layer to more precisely predict the emotion states. In an emotion recognition task with three modalities (EEG, EYE and EIG), we achieve 87.63% accuracy. To deal with the problem that EEG signals are difficult and expensive to collect in practical applications, we achieve 86.28% accuracy with two modalities (EYE and EIG) and propose a new classification paradigm that uses EIG, EYE, and randomly selected EEG data that we have on hand, obtaining 86.81% accuracy.

Overview

Integrity signals

Registry

Crossref · 10.1109/ner49283.2021.9441352

Cites

8 of 8 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 8 references

Cited by

See all 19

Metadata

Authors
Zhao, Z.-W., Liu, W., & Lu, B.-L.
Affiliations
Shanghai Jiao Tong University (CN)
Venue
2021 10th International IEEE/EMBS Conference on Neural Engineering (NER)
Publisher
IEEE
Published
2021-05-04
Pages
73-76
ISSN
1948-3554 (ISSN-L)
OpenAlex
W3167469277
Cited by
19
References
8
Citations by year
2025: 4 · 2024: 5 · 2023: 7 · 2022: 2 · 2021: 1
FWCI
4.17
Type
conference paper
Language
en
Open access
closed
Locations
International IEEE/EMBS Conference on Neural Engineering (publishedVersion)
Funders
  • National Natural Science Foundation of China (61976135)
  • Fundamental Research Funds for the Central Universities
  • China Southern Power Grid (GDKJXM20185761)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
  • Physical Sciences › Computer Science › Human-Computer Interaction › Gaze Tracking and Assistive Technology
  • Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
Keywords
multimodal emotion recognition, EEG, eye movement features, attention-based neural networks, emotion classification

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Multimodal Emotion Recognition Using a Modified Dense Co-Attention Symmetric Network. https://app.cochat.ai/papers/10.1109/ner49283.2021.9441352
The paper
Zhao, Z.-W., Liu, W., & Lu, B.-L. (2021). Multimodal Emotion Recognition Using a Modified Dense Co-Attention Symmetric Network. 2021 10th International IEEE/EMBS Conference on Neural Engineering (NER). https://doi.org/10.1109/ner49283.2021.9441352

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.